Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    JSON, list, table, physical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ene
    0.54
    ia
    0.49
     ફ
    0.49
    ile
    0.46
    ية
    0.46
     বিপরীত
    0.46
    we
    0.44
    ésus
    0.43
    io
    0.43
    ither
    0.43
    POSITIVE LOGITS
    ন
    0.55
     gossip
    0.50
     storylines
    0.50
     Jordi
    0.49
    ش
    0.49
    ޞ
    0.48
    阊
    0.48
    Rom
    0.48
    ม
    0.48
    ។
    0.48
    Act Density 0.000%

    No Known Activations